An Improved YOLOv5 Model for Concrete Bubble Detection Based on Area K-Means and ECANet

气泡 材料科学 机械 物理
作者
Wei Tian,Bazhou Li,Jingjing Cao,Feichao Di,Yang Li,Бо Лю
出处
期刊:Mathematics [Multidisciplinary Digital Publishing Institute]
卷期号:12 (17): 2777-2777
标识
DOI:10.3390/math12172777
摘要

The appearance quality of fair-faced concrete plays a crucial role in evaluating the engineering quality, as the abundance of small-area bubbles generated during construction diminishes the surface quality of concrete. However, existing methods are plagued by sluggish detection speed and inadequate accuracy. Therefore, this paper proposes an improved method based on YOLOv5 to rapidly and accurately detect small bubble defects on the surface of fair-faced concrete. Firstly, to address the issue of YOLOv5 in generating prior boxes for imbalanced samples, we divide the image preprocessing part into small-, medium-, and large-area intervals corresponding to the number of heads. Additionally, we propose an area-based k-means clustering approach specifically tailored for the anchor boxes within each of these intervals. Moreover, we adjust the number of prior boxes generated by k-means clustering according to the training loss function to adapt to bubbles of different sizes. Then, we introduce the ECA (Efficient Channel Attention) mechanism into the neck part of the model to effectively capture inter-channel interactions and enhance feature representation. Subsequently, we incorporate feature concatenation in the neck part to facilitate the fusion of low-level and high-level features, thereby improving the accuracy and generalization ability of the network. Finally, we construct our own dataset containing 980 images of two classes: cement and bubbles. Comparative experiments are conducted on our dataset using YOLOv5s, YOLOv6s, YOLOxs, and our method. Experimental results demonstrate that the proposed method achieves the highest detection accuracy in terms of mAP0.5, mAP0.75, and mAP0.5:0.95. Compared to YOLOv5s, our method achieves a 7.1% improvement in mAP0.5, a 3.7% improvement in mAP0.75, and a 4.5% improvement in mAP0.5:0.95.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
Owen应助受伤幻桃采纳,获得10
4秒前
小生发布了新的文献求助10
6秒前
mou发布了新的文献求助20
7秒前
zy发布了新的文献求助10
8秒前
10秒前
在水一方应助hui采纳,获得10
10秒前
13秒前
13秒前
小生完成签到,获得积分10
14秒前
14秒前
思源应助Wwt采纳,获得10
15秒前
受伤幻桃发布了新的文献求助10
17秒前
laylor发布了新的文献求助80
18秒前
hui完成签到,获得积分10
18秒前
科研通AI2S应助hehexi采纳,获得10
19秒前
20秒前
李fr完成签到 ,获得积分10
21秒前
彭于晏应助果汁采纳,获得10
21秒前
有害学术辣鸡完成签到 ,获得积分10
22秒前
破故纸完成签到,获得积分10
23秒前
hui发布了新的文献求助10
25秒前
moon完成签到,获得积分10
26秒前
希望天下0贩的0应助zzzzzz采纳,获得10
26秒前
cc完成签到,获得积分20
27秒前
jiangjiang完成签到,获得积分10
28秒前
982289172完成签到,获得积分10
28秒前
29秒前
Dadonnggua完成签到 ,获得积分20
30秒前
30秒前
31秒前
量子星尘发布了新的文献求助10
32秒前
catalm关注了科研通微信公众号
32秒前
与非发布了新的文献求助10
33秒前
受伤幻桃发布了新的文献求助10
35秒前
orixero应助PhD_HanWu采纳,获得10
35秒前
36秒前
二手房完成签到,获得积分20
37秒前
FashionBoy应助小强采纳,获得10
38秒前
踏实啤酒完成签到 ,获得积分10
39秒前
戴岱发布了新的文献求助10
40秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 360
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3971469
求助须知:如何正确求助?哪些是违规求助? 3516210
关于积分的说明 11181332
捐赠科研通 3251376
什么是DOI,文献DOI怎么找? 1795810
邀请新用户注册赠送积分活动 876051
科研通“疑难数据库(出版商)”最低求助积分说明 805245